Multi-Class 3D Object Detection with Single-Class Supervision
- URL: http://arxiv.org/abs/2205.05703v1
- Date: Wed, 11 May 2022 18:00:05 GMT
- Title: Multi-Class 3D Object Detection with Single-Class Supervision
- Authors: Mao Ye, Chenxi Liu, Maoqing Yao, Weiyue Wang, Zhaoqi Leng, Charles R.
Qi, Dragomir Anguelov
- Abstract summary: Training multi-class 3D detectors with fully labeled datasets can be expensive.
An alternative approach is to have targeted single-class labels on disjoint data samples.
In this paper, we are interested in training a multi-class 3D object detection model, while using single-class labeled data.
- Score: 34.216636233945856
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: While multi-class 3D detectors are needed in many robotics applications,
training them with fully labeled datasets can be expensive in labeling cost. An
alternative approach is to have targeted single-class labels on disjoint data
samples. In this paper, we are interested in training a multi-class 3D object
detection model, while using these single-class labeled data. We begin by
detailing the unique stance of our "Single-Class Supervision" (SCS) setting
with respect to related concepts such as partial supervision and semi
supervision. Then, based on the case study of training the multi-class version
of Range Sparse Net (RSN), we adapt a spectrum of algorithms -- from supervised
learning to pseudo-labeling -- to fully exploit the properties of our SCS
setting, and perform extensive ablation studies to identify the most effective
algorithm and practice. Empirical experiments on the Waymo Open Dataset show
that proper training under SCS can approach or match full supervision training
while saving labeling costs.
Related papers
- Diverse Teacher-Students for Deep Safe Semi-Supervised Learning under Class Mismatch [35.42630035488178]
We introduce a novel framework named Diverse Teacher-Students (textbfDTS)
By training both teacher-student models with all unlabeled samples, DTS can enhance the classification of seen classes while simultaneously improving the detection of unseen classes.
arXiv Detail & Related papers (2024-05-25T06:54:43Z) - Dual-Perspective Knowledge Enrichment for Semi-Supervised 3D Object
Detection [55.210991151015534]
We present a novel Dual-Perspective Knowledge Enrichment approach named DPKE for semi-supervised 3D object detection.
Our DPKE enriches the knowledge of limited training data, particularly unlabeled data, from two perspectives: data-perspective and feature-perspective.
arXiv Detail & Related papers (2024-01-10T08:56:07Z) - Uni3D: A Unified Baseline for Multi-dataset 3D Object Detection [34.2238222373818]
Current 3D object detection models follow a single dataset-specific training and testing paradigm.
In this paper, we study the task of training a unified 3D detector from multiple datasets.
We present a Uni3D which leverages a simple data-level correction operation and a designed semantic-level coupling-and-recoupling module.
arXiv Detail & Related papers (2023-03-13T05:54:13Z) - LESS: Label-Efficient Semantic Segmentation for LiDAR Point Clouds [62.49198183539889]
We propose a label-efficient semantic segmentation pipeline for outdoor scenes with LiDAR point clouds.
Our method co-designs an efficient labeling process with semi/weakly supervised learning.
Our proposed method is even highly competitive compared to the fully supervised counterpart with 100% labels.
arXiv Detail & Related papers (2022-10-14T19:13:36Z) - Open-Set Semi-Supervised Learning for 3D Point Cloud Understanding [62.17020485045456]
It is commonly assumed in semi-supervised learning (SSL) that the unlabeled data are drawn from the same distribution as that of the labeled ones.
We propose to selectively utilize unlabeled data through sample weighting, so that only conducive unlabeled data would be prioritized.
arXiv Detail & Related papers (2022-05-02T16:09:17Z) - ColloSSL: Collaborative Self-Supervised Learning for Human Activity
Recognition [9.652822438412903]
A major bottleneck in training robust Human-Activity Recognition models (HAR) is the need for large-scale labeled sensor datasets.
Because labeling large amounts of sensor data is an expensive task, unsupervised and semi-supervised learning techniques have emerged.
We present a novel technique called Collaborative Self-Supervised Learning (ColloSSL) which leverages unlabeled data collected from multiple devices.
arXiv Detail & Related papers (2022-02-01T21:05:05Z) - 3D Spatial Recognition without Spatially Labeled 3D [127.6254240158249]
We introduce WyPR, a Weakly-supervised framework for Point cloud Recognition.
We show that WyPR can detect and segment objects in point cloud data without access to any spatial labels at training time.
arXiv Detail & Related papers (2021-05-13T17:58:07Z) - Few-Shot Named Entity Recognition: A Comprehensive Study [92.40991050806544]
We investigate three schemes to improve the model generalization ability for few-shot settings.
We perform empirical comparisons on 10 public NER datasets with various proportions of labeled data.
We create new state-of-the-art results on both few-shot and training-free settings.
arXiv Detail & Related papers (2020-12-29T23:43:16Z) - UniT: Unified Knowledge Transfer for Any-shot Object Detection and
Segmentation [52.487469544343305]
Methods for object detection and segmentation rely on large scale instance-level annotations for training.
We propose an intuitive and unified semi-supervised model that is applicable to a range of supervision.
arXiv Detail & Related papers (2020-06-12T22:45:47Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.